arXiv subjects

Lei Xie

Publications and source records attributed to Lei Xie.

At least 289 records · Page 16Linked to original sources

arXiv2024

LESEN: Label-Efficient deep learning for Multi-parametric MRI-based Visual Pathway Segmentation

Recent research has shown the potential of deep learning in multi-parametric MRI-based visual pathway (VP) segmentation. However, obtaining labeled data for training is laborious and time-consuming. Therefore, it is crucial to develop effective algorithms in situations with limited labeled samples. In this work, we propose a label-efficient deep learning method with self-ensembling (LESEN). LESEN incorporates supervised and unsupervised losses, enabling the student and teacher models to mutually learn from each other, forming a self-ensembling mean teacher framework. Additionally, we introduce a reliable unlabeled sample selection (RUSS) mechanism to further enhance LESEN's effectiveness. Our experiments on the human connectome project (HCP) dataset demonstrate the superior performance of our method when compared to state-of-the-art techniques, advancing multimodal VP segmentation for comprehensive analysis in clinical and research settings. The implementation code will be available at: https://github.com/aldiak/Semi-Supervised-Multimodal-Visual-Pathway- Delineation.

eess.IV↗

arXiv2024

Modality Exchange Network for Retinogeniculate Visual Pathway Segmentation

Accurate segmentation of the retinogeniculate visual pathway (RGVP) aids in the diagnosis and treatment of visual disorders by identifying disruptions or abnormalities within the pathway. However, the complex anatomical structure and connectivity of RGVP make it challenging to achieve accurate segmentation. In this study, we propose a novel Modality Exchange Network (ME-Net) that effectively utilizes multi-modal magnetic resonance (MR) imaging information to enhance RGVP segmentation. Our ME-Net has two main contributions. Firstly, we introduce an effective multi-modal soft-exchange technique. Specifically, we design a channel and spatially mixed attention module to exchange modality information between T1-weighted and fractional anisotropy MR images. Secondly, we propose a cross-fusion module that further enhances the fusion of information between the two modalities. Experimental results demonstrate that our method outperforms existing state-of-the-art approaches in terms of RGVP segmentation performance.

eess.IV↗

arXiv2023

Accent-VITS:accent transfer for end-to-end TTS

Accent transfer aims to transfer an accent from a source speaker to synthetic speech in the target speaker's voice. The main challenge is how to effectively disentangle speaker timbre and accent which are entangled in speech. This paper presents a VITS-based end-to-end accent transfer model named Accent-VITS.Based on the main structure of VITS, Accent-VITS makes substantial improvements to enable effective and stable accent transfer.We leverage a hierarchical CVAE structure to model accent pronunciation information and acoustic features, respectively, using bottleneck features and mel spectrums as constraints.Moreover, the text-to-wave mapping in VITS is decomposed into text-to-accent and accent-to-wave mappings in Accent-VITS. In this way, the disentanglement of accent and speaker timbre becomes be more stable and effective.Experiments on multi-accent and Mandarin datasets show that Accent-VITS achieves higher speaker similarity, accent similarity and speech naturalness as compared with a strong baseline.

cs.SD↗

arXiv2023

PromptVC: Flexible Stylistic Voice Conversion in Latent Space Driven by Natural Language Prompts

Style voice conversion aims to transform the style of source speech to a desired style according to real-world application demands. However, the current style voice conversion approach relies on pre-defined labels or reference speech to control the conversion process, which leads to limitations in style diversity or falls short in terms of the intuitive and interpretability of style representation. In this study, we propose PromptVC, a novel style voice conversion approach that employs a latent diffusion model to generate a style vector driven by natural language prompts. Specifically, the style vector is extracted by a style encoder during training, and then the latent diffusion model is trained independently to sample the style vector from noise, with this process being conditioned on natural language prompts. To improve style expressiveness, we leverage HuBERT to extract discrete tokens and replace them with the K-Means center embedding to serve as the linguistic content, which minimizes residual style information. Additionally, we deduplicate the same discrete token and employ a differentiable duration predictor to re-predict the duration of each token, which can adapt the duration of the same linguistic content to different styles. The subjective and objective evaluation results demonstrate the effectiveness of our proposed system.

eess.AS↗

arXiv2023

Automatic channel selection and spatial feature integration for multi-channel speech recognition across various array topologies

Automatic Speech Recognition (ASR) has shown remarkable progress, yet it still faces challenges in real-world distant scenarios across various array topologies each with multiple recording devices. The focal point of the CHiME-7 Distant ASR task is to devise a unified system capable of generalizing various array topologies that have multiple recording devices and offering reliable recognition performance in real-world environments. Addressing this task, we introduce an ASR system that demonstrates exceptional performance across various array topologies. First of all, we propose two attention-based automatic channel selection modules to select the most advantageous subset of multi-channel signals from multiple recording devices for each utterance. Furthermore, we introduce inter-channel spatial features to augment the effectiveness of multi-frame cross-channel attention, aiding it in improving the capability of spatial information awareness. Finally, we propose a multi-layer convolution fusion module drawing inspiration from the U-Net architecture to integrate the multi-channel output into a single-channel output. Experimental results on the CHiME-7 corpus with oracle segmentation demonstrate that the improvements introduced in our proposed ASR system lead to a relative reduction of 40.1% in the Macro Diarization Attributed Word Error Rates (DA-WER) when compared to the baseline ASR system on the Eval sets.

cs.SD↗

arXiv2023

U2-KWS: Unified Two-pass Open-vocabulary Keyword Spotting with Keyword Bias

Open-vocabulary keyword spotting (KWS), which allows users to customize keywords, has attracted increasingly more interest. However, existing methods based on acoustic models and post-processing train the acoustic model with ASR training criteria to model all phonemes, making the acoustic model under-optimized for the KWS task. To solve this problem, we propose a novel unified two-pass open-vocabulary KWS (U2-KWS) framework inspired by the two-pass ASR model U2. Specifically, we employ the CTC branch as the first stage model to detect potential keyword candidates and the decoder branch as the second stage model to validate candidates. In order to enhance any customized keywords, we redesign the U2 training procedure for U2-KWS and add keyword information by audio and text cross-attention into both branches. We perform experiments on our internal dataset and Aishell-1. The results show that U2-KWS can achieve a significant relative wake-up rate improvement of 41% compared to the traditional customized KWS systems when the false alarm rate is fixed to 0.5 times per hour.

eess.AS↗

arXiv2023

DiAD: A Diffusion-based Framework for Multi-class Anomaly Detection

Reconstruction-based approaches have achieved remarkable outcomes in anomaly detection. The exceptional image reconstruction capabilities of recently popular diffusion models have sparked research efforts to utilize them for enhanced reconstruction of anomalous images. Nonetheless, these methods might face challenges related to the preservation of image categories and pixel-wise structural integrity in the more practical multi-class setting. To solve the above problems, we propose a Difusion-based Anomaly Detection (DiAD) framework for multi-class anomaly detection, which consists of a pixel-space autoencoder, a latent-space Semantic-Guided (SG) network with a connection to the stable diffusion's denoising network, and a feature-space pre-trained feature extractor. Firstly, The SG network is proposed for reconstructing anomalous regions while preserving the original image's semantic information. Secondly, we introduce Spatial-aware Feature Fusion (SFF) block to maximize reconstruction accuracy when dealing with extensively reconstructed areas. Thirdly, the input and reconstructed images are processed by a pre-trained feature extractor to generate anomaly maps based on features extracted at different scales. Experiments on MVTec-AD and VisA datasets demonstrate the effectiveness of our approach which surpasses the state-of-the-art methods, e.g., achieving 96.8/52.6 and 97.2/99.0 (AUROC/AP) for localization and detection respectively on multi-class MVTec-AD dataset. Code will be available at https://lewandofskee.github.io/projects/diad.

cs.CV↗

arXiv2023

Joint Training or Not: An Exploration of Pre-trained Speech Models in Audio-Visual Speaker Diarization

The scarcity of labeled audio-visual datasets is a constraint for training superior audio-visual speaker diarization systems. To improve the performance of audio-visual speaker diarization, we leverage pre-trained supervised and self-supervised speech models for audio-visual speaker diarization. Specifically, we adopt supervised~(ResNet and ECAPA-TDNN) and self-supervised pre-trained models~(WavLM and HuBERT) as the speaker and audio embedding extractors in an end-to-end audio-visual speaker diarization~(AVSD) system. Then we explore the effectiveness of different frameworks, including Transformer, Conformer, and cross-attention mechanism, in the audio-visual decoder. To mitigate the degradation of performance caused by separate training, we jointly train the audio encoder, speaker encoder, and audio-visual decoder in the AVSD system. Experiments on the MISP dataset demonstrate that the proposed method achieves superior performance and obtained third place in MISP Challenge 2022.

eess.AS↗

arXiv2023

Protein Language Model-Powered 3D Ligand Binding Site Prediction from Protein Sequence

Prediction of ligand binding sites of proteins is a fundamental and important task for understanding the function of proteins and screening potential drugs. Most existing methods require experimentally determined protein holo-structures as input. However, such structures can be unavailable on novel or less-studied proteins. To tackle this limitation, we propose LaMPSite, which only takes protein sequences and ligand molecular graphs as input for ligand binding site predictions. The protein sequences are used to retrieve residue-level embeddings and contact maps from the pre-trained ESM-2 protein language model. The ligand molecular graphs are fed into a graph neural network to compute atom-level embeddings. Then we compute and update the protein-ligand interaction embedding based on the protein residue-level embeddings and ligand atom-level embeddings, and the geometric constraints in the inferred protein contact map and ligand distance map. A final pooling on protein-ligand interaction embedding would indicate which residues belong to the binding sites. Without any 3D coordinate information of proteins, our proposed model achieves competitive performance compared to baseline methods that require 3D protein structures when predicting binding sites. Given that less than 50% of proteins have reliable structure information in the current stage, LaMPSite will provide new opportunities for drug discovery.

q-bio.QM↗

arXiv2023

Efficient and Accurate Physics-aware Multiplex Graph Neural Networks for 3D Small Molecules and Macromolecule Complexes

Recent advances in applying Graph Neural Networks (GNNs) to molecular science have showcased the power of learning three-dimensional (3D) structure representations with GNNs. However, most existing GNNs suffer from the limitations of insufficient modeling of diverse interactions, computational expensive operations, and ignorance of vectorial values. Here, we tackle these limitations by proposing a novel GNN model, Physics-aware Multiplex Graph Neural Network (PaxNet), to efficiently and accurately learn the representations of 3D molecules for both small organic compounds and macromolecule complexes. PaxNet separates the modeling of local and non-local interactions inspired by molecular mechanics, and reduces the expensive angle-related computations. Besides scalar properties, PaxNet can also predict vectorial properties by learning an associated vector for each atom. To evaluate the performance of PaxNet, we compare it with state-of-the-art baselines in two tasks. On small molecule dataset for predicting quantum chemical properties, PaxNet reduces the prediction error by 15% and uses 73% less memory than the best baseline. On macromolecule dataset for predicting protein-ligand binding affinities, PaxNet outperforms the best baseline while reducing the memory consumption by 33% and the inference time by 85%. Thus, PaxNet provides a universal, robust and accurate method for large-scale machine learning of molecules. Our code is available at https://github.com/zetayue/Physics-aware-Multiplex-GNN.

q-bio.BM↗

arXiv2023

A Universal Framework for Accurate and Efficient Geometric Deep Learning of Molecular Systems

Molecular sciences address a wide range of problems involving molecules of different types and sizes and their complexes. Recently, geometric deep learning, especially Graph Neural Networks, has shown promising performance in molecular science applications. However, most existing works often impose targeted inductive biases to a specific molecular system, and are inefficient when applied to macromolecules or large-scale tasks, thereby limiting their applications to many real-world problems. To address these challenges, we present PAMNet, a universal framework for accurately and efficiently learning the representations of three-dimensional (3D) molecules of varying sizes and types in any molecular system. Inspired by molecular mechanics, PAMNet induces a physics-informed bias to explicitly model local and non-local interactions and their combined effects. As a result, PAMNet can reduce expensive operations, making it time and memory efficient. In extensive benchmark studies, PAMNet outperforms state-of-the-art baselines regarding both accuracy and efficiency in three diverse learning tasks: small molecule properties, RNA 3D structures, and protein-ligand binding affinities. Our results highlight the potential for PAMNet in a broad range of molecular science applications.

cs.LG↗

arXiv2023

Decoupling and Interacting Multi-Task Learning Network for Joint Speech and Accent Recognition

Accents, as variations from standard pronunciation, pose significant challenges for speech recognition systems. Although joint automatic speech recognition (ASR) and accent recognition (AR) training has been proven effective in handling multi-accent scenarios, current multi-task ASR-AR approaches overlook the granularity differences between tasks. Fine-grained units capture pronunciation-related accent characteristics, while coarse-grained units are better for learning linguistic information. Moreover, an explicit interaction of two tasks can also provide complementary information and improve the performance of each other, but it is rarely used by existing approaches. In this paper, we propose a novel Decoupling and Interacting Multi-task Network (DIMNet) for joint speech and accent recognition, which is comprised of a connectionist temporal classification (CTC) branch, an AR branch, an ASR branch, and a bottom feature encoder. Specifically, AR and ASR are first decoupled by separated branches and two-granular modeling units to learn task-specific representations. The AR branch is from our previously proposed linguistic-acoustic bimodal AR model and the ASR branch is an encoder-decoder based Conformer model. Then, for the task interaction, the CTC branch provides aligned text for the AR task, while accent embeddings extracted from our AR model are incorporated into the ASR branch's encoder and decoder. Finally, during ASR inference, a cross-granular rescoring method is introduced to fuse the complementary information from the CTC and attention decoder after the decoupling. Our experiments on English and Chinese datasets demonstrate the effectiveness of the proposed model, which achieves 21.45%/28.53% AR accuracy relative improvement and 32.33%/14.55% ASR error rate relative reduction over a published standard baseline, respectively.

cs.SD↗

arXiv2023

Sensing Mutual Information with Random Signals in Gaussian Channels

Sensing performance is typically evaluated by classical metrics, such as Cramer-Rao bound and signal-to-clutter-plus-noise ratio. The recent development of the integrated sensing and communication (ISAC) framework motivated the efforts to unify the metric for sensing and communication, where researchers have proposed to utilize mutual information (MI) to measure the sensing performance with deterministic signals. However, the need to communicate in ISAC systems necessitates the use of random signals for sensing applications and the closed-form evaluation for the sensing mutual information (SMI) with random signals is not yet available in the literature. This paper investigates the achievable performance and precoder design for sensing applications with random signals. For that purpose, we first derive the closed-form expression for the SMI with random signals by utilizing random matrix theory. The result reveals some interesting physical insights regarding the relation between the SMI with deterministic and random signals. The derived SMI is then utilized to optimize the precoder by leveraging a manifold-based optimization approach. The effectiveness of the proposed methods is validated by simulation results.

cs.IT↗

arXiv2023

Vec-Tok Speech: speech vectorization and tokenization for neural speech generation

Language models (LMs) have recently flourished in natural language processing and computer vision, generating high-fidelity texts or images in various tasks. In contrast, the current speech generative models are still struggling regarding speech quality and task generalization. This paper presents Vec-Tok Speech, an extensible framework that resembles multiple speech generation tasks, generating expressive and high-fidelity speech. Specifically, we propose a novel speech codec based on speech vectors and semantic tokens. Speech vectors contain acoustic details contributing to high-fidelity speech reconstruction, while semantic tokens focus on the linguistic content of speech, facilitating language modeling. Based on the proposed speech codec, Vec-Tok Speech leverages an LM to undertake the core of speech generation. Moreover, Byte-Pair Encoding (BPE) is introduced to reduce the token length and bit rate for lower exposure bias and longer context coverage, improving the performance of LMs. Vec-Tok Speech can be used for intra- and cross-lingual zero-shot voice conversion (VC), zero-shot speaking style transfer text-to-speech (TTS), speech-to-speech translation (S2ST), speech denoising, and speaker de-identification and anonymization. Experiments show that Vec-Tok Speech, built on 50k hours of speech, performs better than other SOTA models. Code will be available at https://github.com/BakerBunker/VecTok .

cs.SD↗

arXiv2023

BA-MoE: Boundary-Aware Mixture-of-Experts Adapter for Code-Switching Speech Recognition

Mixture-of-experts based models, which use language experts to extract language-specific representations effectively, have been well applied in code-switching automatic speech recognition. However, there is still substantial space to improve as similar pronunciation across languages may result in ineffective multi-language modeling and inaccurate language boundary estimation. To eliminate these drawbacks, we propose a cross-layer language adapter and a boundary-aware training method, namely Boundary-Aware Mixture-of-Experts (BA-MoE). Specifically, we introduce language-specific adapters to separate language-specific representations and a unified gating layer to fuse representations within each encoder layer. Second, we compute language adaptation loss of the mean output of each language-specific adapter to improve the adapter module's language-specific representation learning. Besides, we utilize a boundary-aware predictor to learn boundary representations for dealing with language boundary confusion. Our approach achieves significant performance improvement, reducing the mixture error rate by 16.55\% compared to the baseline on the ASRU 2019 Mandarin-English code-switching challenge dataset.

cs.SD↗

arXiv2023

PromptSpeaker: Speaker Generation Based on Text Descriptions

Recently, text-guided content generation has received extensive attention. In this work, we explore the possibility of text description-based speaker generation, i.e., using text prompts to control the speaker generation process. Specifically, we propose PromptSpeaker, a text-guided speaker generation system. PromptSpeaker consists of a prompt encoder, a zero-shot VITS, and a Glow model, where the prompt encoder predicts a prior distribution based on the text description and samples from this distribution to obtain a semantic representation. The Glow model subsequently converts the semantic representation into a speaker representation, and the zero-shot VITS finally synthesizes the speaker's voice based on the speaker representation. We verify that PromptSpeaker can generate speakers new from the training set by objective metrics, and the synthetic speaker voice has reasonable subjective matching quality with the speaker prompt.

cs.SD↗

arXiv2023

SALT: Distinguishable Speaker Anonymization Through Latent Space Transformation

Speaker anonymization aims to conceal a speaker's identity without degrading speech quality and intelligibility. Most speaker anonymization systems disentangle the speaker representation from the original speech and achieve anonymization by averaging or modifying the speaker representation. However, the anonymized speech is subject to reduction in pseudo speaker distinctiveness, speech quality and intelligibility for out-of-distribution speaker. To solve this issue, we propose SALT, a Speaker Anonymization system based on Latent space Transformation. Specifically, we extract latent features by a self-supervised feature extractor and randomly sample multiple speakers and their weights, and then interpolate the latent vectors to achieve speaker anonymization. Meanwhile, we explore the extrapolation method to further extend the diversity of pseudo speakers. Experiments on Voice Privacy Challenge dataset show our system achieves a state-of-the-art distinctiveness metric while preserving speech quality and intelligibility. Our code and demo is availible at https://github.com/BakerBunker/SALT .

cs.SD↗

arXiv2023

TranUSR: Phoneme-to-word Transcoder Based Unified Speech Representation Learning for Cross-lingual Speech Recognition

UniSpeech has achieved superior performance in cross-lingual automatic speech recognition (ASR) by explicitly aligning latent representations to phoneme units using multi-task self-supervised learning. While the learned representations transfer well from high-resource to low-resource languages, predicting words directly from these phonetic representations in downstream ASR is challenging. In this paper, we propose TranUSR, a two-stage model comprising a pre-trained UniData2vec and a phoneme-to-word Transcoder. Different from UniSpeech, UniData2vec replaces the quantized discrete representations with continuous and contextual representations from a teacher model for phonetically-aware pre-training. Then, Transcoder learns to translate phonemes to words with the aid of extra texts, enabling direct word generation. Experiments on Common Voice show that UniData2vec reduces PER by 5.3% compared to UniSpeech, while Transcoder yields a 14.4% WER reduction compared to grapheme fine-tuning.

eess.AS↗